© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12677
    Prev
    Next
    INDEX
    Explanations

    topics related to recovery and returning to previous states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chaun
    -0.56
    atonic
    -0.54
    MeasureSpec
    -0.52
    rfloor
    -0.52
    مقاله
    -0.52
    ècie
    -0.51
    msgTypes
    -0.51
    ziell
    -0.50
    choly
    -0.50
    Dislikes
    -0.49
    POSITIVE LOGITS
     back
    1.24
     kembali
    1.18
     return
    1.17
     regaining
    1.17
     wieder
    1.16
     returning
    1.15
     regained
    1.15
     returned
    1.14
     regain
    1.11
     restore
    1.10
    Activations Density 0.535%

    No Known Activations